PROJECT TITLE :

Novel Example Based Method for Super-Resolution and Denoising of Medical Images - 2014

ABSTRACT:

In this paper, we have a tendency to propose a completely unique example-based mostly method for denoising and super-resolution of medical images. The objective is to estimate a high-resolution image from one noisy low-resolution image, with the help of a given database of high and low-resolution image patch pairs. Denoising and super-resolution during this paper is performed on each image patch. For each given input low-resolution patch, its high-resolution version is estimated based mostly on finding a nonnegative sparse linear representation of the input patch over the low-resolution patches from the database, where the coefficients of the illustration strongly rely on the similarity between the input patch and therefore the sample patches in the database. The matter of finding the nonnegative sparse linear illustration is modeled as a nonnegative quadratic programming downside. The proposed method is particularly helpful for the case of noise-corrupted and low-resolution image. Experimental results show that the proposed methodology outperforms different state-of-the-art super-resolution strategies while effectively removing noise.